CN115797857B - Travel event determining method, security inspection method and event management method - Google Patents
Travel event determining method, security inspection method and event management method Download PDFInfo
- Publication number
- CN115797857B CN115797857B CN202211384507.2A CN202211384507A CN115797857B CN 115797857 B CN115797857 B CN 115797857B CN 202211384507 A CN202211384507 A CN 202211384507A CN 115797857 B CN115797857 B CN 115797857B
- Authority
- CN
- China
- Prior art keywords
- target
- travel event
- preset
- tested
- package
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Alarm Systems (AREA)
Abstract
The embodiment of the application provides a travel event determining method, a security inspection method and an event management method, wherein the travel event determining method comprises the following steps: determining target article information corresponding to a package to be tested according to an acquired image containing the package to be tested; wherein the target item information characterizes a target item in the package to be tested; determining target occurrence probability of each preset travel event when the target object combination exists according to the target object information; and selecting a target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event. According to the method and the device, the target travel event corresponding to the package to be tested can be accurately determined according to the target occurrence probability of each preset travel event, the travel event integrates the combined influence of several target objects in the package to be tested, and travel scenes corresponding to relevant users are reflected.
Description
Technical Field
The application relates to the technical field of security inspection, in particular to a travel event determining method, a security inspection method and an event management method.
Background
With the development of technology, transportation becomes an important component in production and life. In order to ensure the safety of transportation, the package needs to be checked.
In the related art, a security inspection machine scans a package to obtain an acquisition image, and whether contraband is carried in the package is determined according to the acquisition image.
However, the above manner only considers the influence of a single item, and the damage degree of the item may be different in different travel scenes, so a method for determining travel information is needed.
Disclosure of Invention
The embodiment of the application provides a travel event determining method, a security inspection method and an event management method, which are used for accurately determining travel related information corresponding to packages.
In a first aspect, an embodiment of the present application provides a travel event determining method based on a package acquired image, including:
determining target article information corresponding to a package to be tested according to an acquired image containing the package to be tested; wherein the target item information characterizes a target item in the package to be tested;
determining target occurrence probability of each preset travel event when the target object combination exists according to the target object information;
And selecting a target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event.
According to the scheme, after the acquired image containing the package to be tested is acquired, the target object information representing the target object in the package to be tested is determined; further, according to the target item information, determining the target occurrence probability of each preset travel event when the target item combination in the package to be tested exists, namely the occurrence probability of each preset travel event; because the target occurrence probability of each preset travel event represents the occurrence probability of each preset travel event when several target objects in the package to be tested coexist, the target travel event corresponding to the package to be tested can be accurately determined according to the target occurrence probability of each preset travel event, and the travel event integrates the combined influence of the several target objects in the package to be tested and reflects the travel scene corresponding to the relevant user.
In some optional embodiments, determining, according to the target item information, a target occurrence probability of each preset travel event when the target item combination exists includes:
And inputting the target object information into a probabilistic reasoning model, and determining the target occurrence probability of each preset travel event according to the preset probability information and the target object information through the probabilistic reasoning model.
In some optional embodiments, the preset probability information includes a first probability that each preset item exists independently when any preset travel event occurs, and a preset occurrence probability of each preset travel event; according to the preset probability information and the target object information, determining the target occurrence probability of each preset travel event comprises the following steps:
for any preset travel event, carrying out continuous multiplication on first probabilities of independent existence of all target objects when the preset travel event occurs, and obtaining second probabilities of combined existence of all the target objects when the preset travel event occurs;
multiplying the second probability with the preset occurrence probability of the preset travel event to obtain a probability product;
and determining the ratio between the probability product and the third probability of the combined existence of all the target objects as the target occurrence probability of the preset travel event.
In some alternative embodiments, the probabilistic inference model comprises a bayesian network.
In some optional embodiments, according to the target occurrence probability of each preset travel event, selecting a target travel event corresponding to the package to be tested from all preset travel events, including:
and determining a preset travel event corresponding to the maximum value of the target occurrence probability as a target travel event corresponding to the package to be tested.
In some optional embodiments, according to the target occurrence probability of each preset travel event, selecting a target travel event corresponding to the package to be tested from all preset travel events, including:
determining a preset travel event with the target occurrence probability larger than the occurrence probability threshold as a candidate travel event;
if a plurality of candidate travel events exist, determining the candidate travel event with the highest weight as a target travel event corresponding to the package to be tested; if one candidate travel event exists, determining the candidate travel event as a target travel event corresponding to the package to be tested.
In some optional embodiments, determining, according to an acquired image including a package to be tested, target item information corresponding to the package to be tested includes:
inputting the acquired image into an object recognition model, carrying out object recognition on the acquired image through the object recognition model, and determining object information of a recognition object and a confidence coefficient corresponding to the recognition object;
If the confidence coefficient corresponding to the identification object is larger than the preset confidence coefficient, determining the object information of the identification object as the target object information; otherwise, determining the object information of the identified object as background information.
In a second aspect, an embodiment of the present application provides a security inspection method, including:
determining whether information representing forbidden articles exists in target article information corresponding to the package to be tested;
if the information representing the forbidden articles exists in the target article information, judging whether the package to be tested passes security inspection or not according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested; wherein the target travel event is determined based on the method of any one of the first aspects;
and if the information of the forbidden articles is not represented in the information of the target articles, judging that the package to be tested passes the security check.
According to the scheme, as the travel event synthesizes the combined influence of the plurality of target objects in the package to be tested, the travel scene corresponding to the relevant user is reflected, the damage degree of the objects in different travel events is different, and when information representing forbidden objects exists in the target object information, whether the package to be tested passes the security check is more reasonably determined by considering the combined influence of the plurality of target objects in the package to be tested.
In some optional embodiments, determining whether the package to be tested passes the security check according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested, includes:
if the target travel event represents safe travel and the information representing forbidden articles is in an article set corresponding to the target travel event, judging that the package to be tested passes security inspection; otherwise, judging that the package to be tested does not pass the security check;
wherein the item set includes item information for the desired item when the target travel event occurs.
In a third aspect, an embodiment of the present application provides an event management method, including:
determining the occurrence times of each target travel event in a target travel event sequence according to the target travel event sequence corresponding to all packages to be tested in the region to be tested in a preset period; wherein the target travel event corresponding to each package to be tested is determined based on the method of any one of the first aspects;
for any target travel event, if the occurrence times of the target travel event exceeds the preset times corresponding to the target travel event, notifying an event message in a preset notification mode; the event message comprises the target travel event and information representing the region to be tested.
According to the scheme, as the travel events integrate the combined influence of the several target objects in the packages to be tested, the travel scene corresponding to the relevant user is reflected, the occurrence times of each target travel event are determined by determining the target travel event corresponding to each package to be tested in a certain to-be-tested area within a preset period, when the occurrence times of the target travel event exceed the preset times corresponding to the target travel event, the fact that the target travel event occurs frequently is indicated, event information is notified through a preset notification mode, relevant personnel can conveniently acquire that the target travel event is abnormal, and corresponding management and control are timely carried out.
In a fourth aspect, an embodiment of the present application provides a travel event determining device based on a package acquired image, including:
the article determining module is used for determining target article information corresponding to the package to be tested according to the acquired image containing the package to be tested; wherein the target item information characterizes a target item in the package to be tested;
the probability determining module is used for determining the target occurrence probability of each preset travel event when the target object combination exists according to the target object information;
The event determining module is used for selecting the target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event.
In some optional embodiments, the probability determining module is specifically configured to:
and inputting the target object information into a probabilistic reasoning model, and determining the target occurrence probability of each preset travel event according to the preset probability information and the target object information through the probabilistic reasoning model.
In some optional embodiments, the preset probability information includes a first probability that each preset item exists independently when any preset travel event occurs, and a preset occurrence probability of each preset travel event; the probability determining module is specifically configured to:
for any preset travel event, carrying out continuous multiplication on first probabilities of independent existence of all target objects when the preset travel event occurs, and obtaining second probabilities of combined existence of all the target objects when the preset travel event occurs;
multiplying the second probability with the preset occurrence probability of the preset travel event to obtain a probability product;
and determining the ratio between the probability product and the third probability of the combined existence of all the target objects as the target occurrence probability of the preset travel event.
In some alternative embodiments, the probabilistic inference model comprises a bayesian network.
In some optional embodiments, the event determination module is specifically configured to:
and determining a preset travel event corresponding to the maximum value of the target occurrence probability as a target travel event corresponding to the package to be tested.
In some optional embodiments, the event determination module is specifically configured to:
determining a preset travel event with the target occurrence probability larger than the occurrence probability threshold as a candidate travel event;
if a plurality of candidate travel events exist, determining the candidate travel event with the highest weight as a target travel event corresponding to the package to be tested; if one candidate travel event exists, determining the candidate travel event as a target travel event corresponding to the package to be tested.
In some alternative embodiments, the article determination module is specifically configured to:
inputting the acquired image into an object recognition model, carrying out object recognition on the acquired image through the object recognition model, and determining object information of a recognition object and a confidence coefficient corresponding to the recognition object;
if the confidence coefficient corresponding to the identification object is larger than the preset confidence coefficient, determining the object information of the identification object as the target object information; otherwise, determining the object information of the identified object as background information.
In a fifth aspect, an embodiment of the present application provides a security inspection device, including:
the contraband determining module is used for determining whether information representing contraband exists in target article information corresponding to the package to be detected;
the security check processing module is used for judging whether the package to be tested passes security check or not according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested if the information representing the forbidden articles exists in the target article information; wherein the target travel event is determined based on the method of any one of the first aspects;
and if the information of the forbidden articles is not represented in the information of the target articles, judging that the package to be tested passes the security check.
In some optional embodiments, the security inspection processing module is specifically configured to:
if the target travel event represents safe travel and the information representing forbidden articles is in an article set corresponding to the target travel event, judging that the package to be tested passes security inspection; otherwise, judging that the package to be tested does not pass the security check;
wherein the item set includes item information for the desired item when the target travel event occurs.
In a sixth aspect, an embodiment of the present application provides an event management apparatus, including:
the event number determining module is used for determining the occurrence number of each target travel event in the target travel event sequence according to the target travel event sequence corresponding to all packages to be tested in the region to be tested in the preset period; wherein the target travel event corresponding to each package to be tested is determined based on the method of any one of the first aspects;
the notification module is used for notifying event messages in a preset notification mode if the occurrence times of the target travel events exceed the preset times corresponding to the target travel events aiming at any target travel event; the event message comprises the target travel event and information representing the region to be tested.
In a seventh aspect, an embodiment of the present application provides an electronic device, where the electronic device includes at least one processor and at least one memory, where the memory stores a computer program that, when executed by the processor, causes the processor to perform the method of any one of the first aspect, the second aspect, or the third aspect.
In an eighth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program executable by an electronic device, the program when run on the electronic device causing the electronic device to perform the method of any one of the first, second or third aspects.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;
fig. 2 is a flow chart of a travel event determining method based on a package collection image according to an embodiment of the present application;
FIG. 3A is a schematic diagram of a network base module of an X-ray image object detection model according to an embodiment of the present application;
fig. 3B is a schematic structural diagram of an X-ray image object detection model according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a bayesian network according to an embodiment of the present application;
fig. 5 is a schematic flow chart of a security inspection method provided in an embodiment of the present application;
fig. 6 is a schematic diagram of a correspondence between a preset travel event and a required article according to an embodiment of the present application;
fig. 7 is a flow chart of an event management method according to an embodiment of the present application;
Fig. 8 is a schematic structural diagram of a travel event determining device based on a package collection image according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a security inspection device according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an event management device according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of promoting an understanding of the principles and advantages of this application, reference will now be made in detail to the drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In transportation, in order to ensure the safety of transportation, the package needs to be checked.
In the related art, a security inspection machine scans a package to obtain an acquisition image, and whether contraband is carried in the package is determined according to the acquisition image.
However, the above approach only considers the impact of a single item, and the extent of damage to the item may be different in different travel scenarios. For example, a folding knife is carried, one case is placed in a tool box together with other finishing tools, and the other case is placed together with rubber gloves, clothes and the like; the folding knife placed in a tool box with the finishing tool may be used for finishing, but the folding knife placed together with rubber gloves, clothes, etc. may be used as a working tool, the risk levels of which are obviously different.
In view of this, the embodiment of the application provides a travel event determining method, a security inspection method and an event management method, which are used for accurately determining travel related information corresponding to a package.
Referring to fig. 1, an application scenario provided in an embodiment of the present application includes an electronic device 100 and at least one security inspection machine 200 (such as a security inspection X-ray machine); the electronic device 100 and the security inspection machine 200 can interact through at least one communication mode;
The security inspection machine 200 is configured to collect an collected image (such as an X-ray image) containing a package to be inspected, and send the collected image to the electronic device 100;
the electronic device 100 is configured to: after receiving the acquired image of the package to be tested, determining target item information (representing target items in the package to be tested) corresponding to the package to be tested; determining the target occurrence probability of each preset travel event when the target object combination exists according to the target object information; and selecting a target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event.
According to the scheme, after the acquired image containing the package to be tested is acquired, the target object information representing the target object in the package to be tested is determined; further, according to the target item information, determining the target occurrence probability of each preset travel event when the target item combination in the package to be tested exists, namely the occurrence probability of each preset travel event; because the target occurrence probability of each preset travel event represents the occurrence probability of each preset travel event when several target objects in the package to be tested coexist, the target travel event corresponding to the package to be tested can be accurately determined according to the target occurrence probability of each preset travel event, and the travel event integrates the combined influence of the several target objects in the package to be tested and reflects the travel scene corresponding to the relevant user.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with reference to the accompanying drawings and specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
Fig. 2 is a flow chart of a travel event determining method based on a package collection image according to an embodiment of the present application, as shown in fig. 2, including the following steps:
step S201: and determining target article information corresponding to the package to be tested according to the acquired image containing the package to be tested.
The target item information characterizes target items in the package to be tested.
In the implementation, the combination of the articles in the package to be tested reflects the travel scene corresponding to the relevant user (the passenger carrying the package to be tested) to a certain extent, such as the travel purpose of the user, the intention of carrying the package and the like; based on the above, it is necessary to determine the target item information corresponding to the package to be tested, that is, which target items are in the package to be tested.
The target article information is not particularly limited in this embodiment, and may be a name, a logo, or the like of the target article, so long as the target article can be uniquely characterized.
Step S202: and determining the target occurrence probability of each preset travel event when the target object combination exists according to the target object information.
In the implementation, when the combination of the objects is different, the occurrence probability of each event is different, for example, more decoration tools exist in the package, the occurrence probability of the decoration event is higher, and the probability of suspicious travel is lower;
based on the information, determining target article information representing a target article in the package to be tested; the target occurrence probability of each preset travel event, that is, the occurrence probability of each preset travel event when the target item combination in the package to be tested exists, needs to be determined based on the target item information.
Step S203: and selecting a target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event.
In this embodiment, since the target occurrence probability of each preset travel event characterizes the probability of occurrence of each preset travel event when the target objects coexist, the target travel event corresponding to the package to be tested can be accurately determined according to the target occurrence probability of each preset travel event.
The method can conveniently and efficiently determine the target travel event corresponding to the package to be tested without active cooperation of users.
According to the scheme, after the acquired image containing the package to be tested is acquired, the target object information representing the target object in the package to be tested is determined; further, according to the target item information, determining the target occurrence probability of each preset travel event when the target item combination in the package to be tested exists, namely the occurrence probability of each preset travel event; because the target occurrence probability of each preset travel event represents the occurrence probability of each preset travel event when several target objects in the package to be tested coexist, the target travel event corresponding to the package to be tested can be accurately determined according to the target occurrence probability of each preset travel event, and the travel event integrates the combined influence of the several target objects in the package to be tested and reflects the travel scene corresponding to the relevant user.
In some alternative embodiments, the step S201 may be implemented by, but not limited to, the following ways:
inputting the acquired image into an object recognition model, carrying out object recognition on the acquired image through the object recognition model, and determining object information of a recognition object and a confidence coefficient corresponding to the recognition object;
If the confidence coefficient corresponding to the identification object is larger than the preset confidence coefficient, determining the object information of the identification object as the target object information; otherwise, determining the object information of the identified object as background information.
The object recognition model can recognize objects in the acquired image and determine the confidence corresponding to each object;
if the confidence coefficient corresponding to a certain object is larger than the preset confidence coefficient, indicating that the object exists, determining the object as a target object, and determining object information of the object as target object information; and if the confidence corresponding to the certain object is smaller than or equal to the preset confidence, indicating that the object is not present, and determining the object as a background.
In some alternative embodiments, the object recognition model is a trained X-ray image object detection model of the self-attention mechanism.
The present embodiment may obtain an X-ray image object detection model of the self-attention mechanism by, but not limited to, the following:
1. and constructing a network basic module, wherein the network basic module comprises a ConvBNL module, an E-ELAN module, a ConvPool module, an SPPCSPC module, an E-ELAN-S module and a REP module. Referring to fig. 3A and 3B, the ConvBNL module is composed of a convolution layer (Convolutional Layer), a normalization layer (Batch Normalization), and an activation function (e.g., a leak ReLU). The E-ELAN module is an extended high-efficiency layer aggregation network, the network is converged more quickly by controlling a gradient path, and the information interaction of the network is realized by using a channel rearrangement technology. The ConvPool module consists of a convolutional layer and a pooling layer. The SPPCSPC module consists of a ConvBNL module and a layered pooling layer. The E-ELAN-S module consists of a multi-path ConvBNL module. The REP module consists of a convolution layer and a normalization layer, and adopts different network structures at the training end and the detection end so as to improve the reasoning speed of the detection end. A Multi-Head Self-Attention (Multi-Head Self-Attention) module is inserted into a network module of Multi-layer feature extraction to improve feature extraction capabilities for various resolution size targets.
2. After the network basic module is constructed, taking a sample image in a training set, article information of an article actually contained in a corresponding sample image and coordinates of the article in the image as input, taking predicted article information as output, taking similarity between the predicted article information and the article information of the article actually contained in the corresponding sample image as an optimization function, and setting different parameters in stages for training to obtain an X-ray image target detection model; after the X-ray image is input into the X-ray image target detection model, the X-ray image target detection model outputs object information of the identified object and corresponding confidence.
In practice, in order to make the recognition result of the X-ray image target detection model more accurate, a training set containing abundant objects needs to be used, for example, frequent articles and rare articles are found in the training set, various cups, cutters, tools, stationery, cosmetics, foods, medicines and the like are involved, and each article appears 2000-5000 times in the training set.
The above models and training sets required for training are only exemplary, and the present application is not limited thereto.
In some alternative embodiments, the step S202 may be implemented by, but not limited to, the following ways:
And inputting the target object information into a probabilistic reasoning model, and determining the target occurrence probability of each preset travel event according to the preset probability information and the target object information through the probabilistic reasoning model.
The probability inference model is configured with preset probability information, target object information is input into the probability inference model, and the probability inference model determines the target occurrence probability of each preset travel event according to the preset probability information and the target object information.
In some alternative embodiments, the probabilistic inference model includes a bayesian network.
The bayesian network is provided with a father node and a child node, wherein a preset trip event is taken as the father node, and article information is taken as the child node. The number of the father nodes (how many preset travel events need to be set) and the number of the child nodes (how many articles are involved) can be determined according to the actual application scene;
referring to fig. 4, the number of preset travel events corresponding to the bayesian network is M, and the number of corresponding articles is N; the M preset travel events can be inferred through the Bayesian network, namely, the target occurrence probability of the M preset travel events can be obtained for each input X-ray image.
It should be noted that the number of the preset travel events corresponding to the bayesian network may be one or more, and the set number of the preset travel events corresponding to each probabilistic reasoning model is also one or more.
In some optional embodiments, in the bayesian network, the preset probability information includes a first probability that each preset item exists independently when any preset travel event occurs, and a preset occurrence probability of each preset travel event;
correspondingly, in the Bayesian network, according to the preset probability information and the target object information, the target occurrence probability of each preset travel event is determined by the following manner:
for any preset travel event, carrying out continuous multiplication on first probabilities of independent existence of all target objects when the preset travel event occurs, and obtaining second probabilities of combined existence of all the target objects when the preset travel event occurs;
multiplying the second probability with the preset occurrence probability of the preset travel event to obtain a probability product;
and determining the ratio between the probability product and the third probability of the combined existence of all the target objects as the target occurrence probability of the preset travel event.
Illustratively, the package to be tested has N target items, namely item 1, item 2, … …, item N (the N items being part of the N items);
for the x-th preset travel event TPx, the second probabilityWherein P (O) i I TPx) is a first probability that the item i exists alone when the preset travel event TPx occurs;
probability product P Product of =P(O Combination n TPx) P (TPx); wherein P (TPx) is a preset occurrence probability of a preset travel event TPx;
target occurrence probability P (tpx|o) of preset travel event TPx Combination n )=P Product of /P(O Combination n );P(O Combination n ) A third probability of combined presence for all target items;
namely P (TPx|O) Combination n )=[P(O Combination n |TPx)*P(TPx)]/P(O Combination n ) -expressed as equation 1.
The preset occurrence probability can be set according to an actual application scene, for example, the preset travel event is a shift, and then the proportion of the shift-up passengers is counted in an inquiry mode to obtain the preset occurrence probability of the shift-up preset travel event; or when the ratio of the occurrence of the preset travel event to the non-occurrence of the preset travel event is similar, the preset occurrence probability of the occurrence of the preset travel event and the non-occurrence of the preset travel event may be set to 0.5, which is not illustrated here.
The third probability that all of the above-described target item combinations exist may be determined by:
P(~TPx|O combination n )=[P(O Combination n |~TPx)*P(~TPx)]/P(O Combination n ) -denoted as equation 2;
wherein P (-TPx|O) Combination n ) For the target occurrence probability of the non-preset travel event TPx, P (O Combination n The value of the total number of the target objects is equal to the first probability that the target objects exist in combination when the non-preset travel event occurs, and the value of the total number of the target objects is equal to the second probability that the target objects exist in combination when the non-preset travel event occurs, wherein the value of the total number of the target objects is equal to the second probability that the non-preset travel event occurs, and the value of the total number of the target objects is equal to the first probability that the non-preset travel event occurs Combination n ) A third probability of combined presence for all of the target items;
since the sum of P (-TPx) and P (TPx) is 1, P (TPx|O Combination n ) And P (-TPx|O) Combination n ) The sum is 1, so the third probability that all the target objects exist in combination and the target occurrence probability of the preset travel event can be obtained based on the formula 1 and the formula 2.
It will be appreciated that in practice, the package to be tested will contain different items and combinations of items.
In some alternative embodiments, the step S203 may be implemented by, but not limited to, the following ways:
mode 1: and determining a preset travel event corresponding to the maximum value of the target occurrence probability as a target travel event corresponding to the package to be tested.
Taking the M preset travel events as an example, determining the target occurrence probability of each preset travel event in the mode; and selecting a preset travel event corresponding to the maximum target occurrence probability from the preset travel event as a target travel event corresponding to the package to be tested.
Mode 2: determining a preset travel event with the target occurrence probability larger than the occurrence probability threshold as a candidate travel event;
if a plurality of candidate travel events exist, determining the candidate travel event with the highest weight as a target travel event corresponding to the package to be tested; if one candidate travel event exists, determining the candidate travel event as a target travel event corresponding to the package to be tested.
In this embodiment, each preset travel event corresponds to a weight value, and the weight value corresponding to the travel event with higher risk level is higher.
Taking the M preset travel events as an example, determining the target occurrence probability of each preset travel event in the mode; selecting a preset travel event corresponding to a target occurrence probability greater than an occurrence probability threshold from the event types as a candidate travel event corresponding to the package to be tested (namely, the occurrence probabilities of the travel events are relatively high); and then determining the candidate travel event with the highest weight as the target travel event corresponding to the package to be tested, so that the occurrence probability and the importance of the event can be balanced, and the target travel event can be selected more pertinently, thereby effectively preventing travel events with higher risk degree.
Fig. 5 is a flow chart of a security inspection method provided in an embodiment of the present application, as shown in fig. 5, including the following steps:
step S501: and determining whether information representing forbidden articles exists in the target article information corresponding to the package to be tested.
In the actual security inspection process, determining whether the target object has forbidden objects or not through an intelligent graph judging end or a manual graph judging end, namely whether the target object information has information representing the forbidden objects or not; thereby determining whether the package to be tested passes the security check.
In some scenes, some forbidden articles are articles required by the occurrence of the event, the forbidden articles have low hazard degree in the corresponding event, and if only the information representing the forbidden articles in the target article information is determined, the passengers are judged to have no security check, so that the normal travel of the passengers can be influenced.
Based on this, when determining that the information representing the forbidden articles exists in the target article information, the embodiment executes step S502, and determines whether the package to be tested passes the security check according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested (i.e. combining with the actual travel scene); otherwise, if no information characterizing the forbidden articles is determined in the target article information, step S503 is executed, i.e. it is determined that the package to be tested passes the security check.
Step S502: if the information representing the forbidden articles exists in the target article information, judging whether the package to be tested passes security inspection or not according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested.
The determination manner of the target trip event may refer to the above embodiment, and will not be described herein.
Step S503: and if the information of the forbidden articles is not represented in the information of the target articles, judging that the package to be tested passes the security check.
According to the scheme, as the travel event synthesizes the combined influence of the plurality of target objects in the package to be tested, the travel scene corresponding to the relevant user is reflected, the damage degree of the objects in different travel events is different, and when information representing forbidden objects exists in the target object information, whether the package to be tested passes the security check is more reasonably determined by considering the combined influence of the plurality of target objects in the package to be tested.
In some alternative embodiments, the step S502 may be implemented by, but not limited to, the following ways:
if the target travel event represents safe travel and the information representing forbidden articles is in an article set corresponding to the target travel event, judging that the package to be tested passes security inspection; otherwise, judging that the package to be tested does not pass the security check;
Wherein the item set includes item information for the desired item when the target travel event occurs.
The trip event representing the safe trip is an event such as a trip event with low potential safety hazard and no harm to other people or society, such as a shift, an outdoor exercise, engineering maintenance, medical treatment, school, a music class, a remote trip, a business trip or a travel; correspondingly, the trip event representing unsafe trip is a trip event with higher potential safety hazards such as suspicious trip.
Referring to fig. 6, a correspondence exists between a preset travel event and a required item (the correspondence may refer to an association relationship between a parent node and a child node in a bayesian network);
if the event itself represents a safe trip and forbidden articles required by the event occur under the event, the forbidden articles have low hazard degree under the scene, and the package to be tested is allowed to pass the security check;
if the event itself represents unsafe travel, the event has a great hidden trouble, and the package to be tested is not allowed to pass the security check;
if the forbidden articles are not the articles required by the occurrence of the event, the fact that the hazard degree is large under the event is indicated, and the packages to be tested are not allowed to pass the security check is not allowed, so that the requirements of different scenes are met.
The above-mentioned four preset travel events of working, outdoor exercises, engineering maintenance and suspicious travel are taken as examples in fig. 6, and preset travel events such as medical treatment, learning, music lessons, remote travel, business trip or travel may also occur in practical application, which are not taken as examples.
Fig. 7 is a flow chart of an event management method according to an embodiment of the present application, as shown in fig. 7, including the following steps:
step S701: and determining the occurrence times of each target travel event in the target travel event sequence according to the target travel event sequence corresponding to all packages to be tested in the region to be tested in the preset period.
The determination manner of the target travel event corresponding to each package to be tested can refer to the above embodiment, and will not be described herein again.
In implementation, when a large number of identical events occur in a short time in one area, risks may exist, based on which, in this embodiment, the occurrence times of each target travel event need to be counted according to a target travel event sequence (a sequence obtained by combining target travel events corresponding to all packages to be tested in the area to be tested in a preset period).
Step S702: and aiming at any target travel event, if the occurrence times of the target travel event exceeds the preset times corresponding to the target travel event, notifying an event message in a preset notification mode.
The event message comprises the target travel event and information representing the region to be tested.
For example, if the occurrence number of a certain target travel event exceeds the preset number corresponding to the target travel event, it is indicated that a risk may exist when a large number of identical events occur in the region to be tested in a short time; and then, notifying the target trip event and the information representing the region to be tested in a preset notification mode, so that related personnel can timely learn the event possibly with risk and the region to be tested, and further taking corresponding management and control measures.
For example: in the field of security and protection of rail transit security, public security is very important, and when the occurrence frequency of suspicious travel events exceeds the corresponding preset frequency, relevant personnel are notified so as to increase security and protection force in time; if the occurrence frequency of the event exceeds the corresponding preset frequency, deducing that the corresponding region is a region with more concentrated patients, informing relevant personnel, and pertinently adding public infrastructure to improve convenience.
In implementation, different preset times can be set for different areas and different target travel events.
According to the scheme, as the travel events integrate the combined influence of the several target objects in the packages to be tested, the travel scene corresponding to the relevant user is reflected, the occurrence times of each target travel event are determined by determining the target travel event corresponding to each package to be tested in a certain to-be-tested area within a preset period, when the occurrence times of the target travel event exceed the preset times corresponding to the target travel event, the fact that the target travel event occurs frequently is indicated, event information is notified through a preset notification mode, relevant personnel can conveniently acquire that the target travel event is abnormal, and corresponding management and control are timely carried out.
Based on the same inventive concept, the embodiment of the present application provides a travel event determining device based on a package acquired image, referring to fig. 8, the travel event determining device 800 includes:
the article determining module 801 is configured to determine target article information corresponding to a package to be tested according to an acquired image including the package to be tested; wherein the target item information characterizes a target item in the package to be tested;
the probability determining module 802 is configured to determine, according to the target item information, a target occurrence probability of each preset travel event when the target item combination exists;
The event determining module 803 is configured to select, according to the target occurrence probability of each preset travel event, a target travel event corresponding to the package to be tested from all preset travel events.
In some alternative embodiments, the probability determination module 802 is specifically configured to:
and inputting the target object information into a probabilistic reasoning model, and determining the target occurrence probability of each preset travel event according to the preset probability information and the target object information through the probabilistic reasoning model.
In some optional embodiments, the preset probability information includes a first probability that each preset item exists independently when any preset travel event occurs, and a preset occurrence probability of each preset travel event; the probability determination module 802 is specifically configured to:
for any preset travel event, carrying out continuous multiplication on first probabilities of independent existence of all target objects when the preset travel event occurs, and obtaining second probabilities of combined existence of all the target objects when the preset travel event occurs;
multiplying the second probability with the preset occurrence probability of the preset travel event to obtain a probability product;
and determining the ratio between the probability product and the third probability of the combined existence of all the target objects as the target occurrence probability of the preset travel event.
In some alternative embodiments, the probabilistic inference model comprises a bayesian network.
In some alternative embodiments, the event determination module 803 is specifically configured to:
and determining a preset travel event corresponding to the maximum value of the target occurrence probability as a target travel event corresponding to the package to be tested.
In some alternative embodiments, the event determination module 803 is specifically configured to:
determining a preset travel event with the target occurrence probability larger than the occurrence probability threshold as a candidate travel event;
if a plurality of candidate travel events exist, determining the candidate travel event with the highest weight as a target travel event corresponding to the package to be tested; if one candidate travel event exists, determining the candidate travel event as a target travel event corresponding to the package to be tested.
In some alternative embodiments, the article determination module 801 is specifically configured to:
inputting the acquired image into an object recognition model, carrying out object recognition on the acquired image through the object recognition model, and determining object information of a recognition object and a confidence coefficient corresponding to the recognition object;
if the confidence coefficient corresponding to the identification object is larger than the preset confidence coefficient, determining the object information of the identification object as the target object information; otherwise, determining the object information of the identified object as background information.
Because the trip event determining device is a device corresponding to the trip event method in the embodiment of the present application, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repetition is omitted.
Based on the same inventive concept, an embodiment of the present application provides a security inspection device, referring to fig. 9, a security inspection device 900 includes:
the contraband determining module 901 is used for determining whether information representing contraband exists in target item information corresponding to the package to be detected;
the security check processing module 902 is configured to determine whether the package to be tested passes a security check according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested if the information representing the forbidden articles exists in the target article information; wherein the target travel event is determined based on the above embodiment;
and if the information of the forbidden articles is not represented in the information of the target articles, determining that the package to be tested passes the security check.
In some optional embodiments, the security check processing module 902 is specifically configured to:
if the target travel event represents safe travel and the information representing forbidden articles is in an article set corresponding to the target travel event, judging that the package to be tested passes security inspection; otherwise, judging that the package to be tested does not pass the security check;
Wherein the item set includes item information for the desired item when the target travel event occurs.
Since the security inspection device is the device corresponding to the security inspection method in the embodiment of the application, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repetition is omitted.
Based on the same inventive concept, an embodiment of the present application provides an event management apparatus, referring to fig. 10, an event management apparatus 1000 includes:
the event number determining module 1001 is configured to determine, according to a target travel event sequence corresponding to all packages to be tested in an area to be tested in a preset period, the occurrence number of each target travel event in the target travel event sequence; the target travel event corresponding to each package to be tested is determined based on the embodiment;
a notification module 1002, configured to notify, for any target travel event, an event message by a preset notification manner if the occurrence number of the target travel event exceeds a preset number corresponding to the target travel event; the event message comprises the target travel event and information representing the region to be tested.
Since the security inspection device is the device corresponding to the security inspection method in the embodiment of the application, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repetition is omitted.
Based on the same technical concept, the embodiment of the present application further provides an electronic device 1100, as shown in fig. 11, including at least one processor 1101 and a memory 1102 connected to the at least one processor, where a specific connection medium between the processor 1101 and the memory 1102 is not limited in the embodiment of the present application, and in fig. 11, the processor 1101 and the memory 1102 are connected by a bus 1103 for example. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in FIG. 11, but not only one bus or one type of bus.
The processor 1101 is a control center of the electronic device, and may be connected to various parts of the electronic device by various interfaces and lines, and execute instructions stored in the memory 1102 and invoke data stored in the memory 1102, thereby implementing data processing. Alternatively, the processor 1101 may include one or more processing units, and the processor 1101 may integrate an application processor and a modem processor, wherein the application processor primarily processes an operating system, a user interface, an application program, and the like, and the modem processor primarily processes issuing instructions. It will be appreciated that the modem processor described above may not be integrated into the processor 1101. In some embodiments, the processor 1101 and the memory 1102 may be implemented on the same chip, and in some embodiments they may be implemented separately on separate chips.
The processor 1101 may be a general purpose processor such as a Central Processing Unit (CPU), digital signal processor, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, that can implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments described above may be embodied directly in hardware, in a processor, or in a combination of hardware and software modules in a processor.
Memory 1102 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The Memory 1102 may include at least one type of storage medium, and may include, for example, flash Memory, hard disk, multimedia card, card Memory, random access Memory (Random Access Memory, RAM), static random access Memory (Static Random Access Memory, SRAM), programmable Read-Only Memory (Programmable Read Only Memory, PROM), read-Only Memory (ROM), charged erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory), magnetic Memory, magnetic disk, optical disk, and the like. Memory 1102 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 1102 in the present embodiment may also be circuitry or any other device capable of implementing a memory function for storing program instructions and/or data.
In the present embodiment, the memory 1102 stores a computer program that, when executed by the processor 1101, causes the processor 1101 to perform:
determining target article information corresponding to a package to be tested according to an acquired image containing the package to be tested; wherein the target item information characterizes a target item in the package to be tested;
determining target occurrence probability of each preset travel event when the target object combination exists according to the target object information;
and selecting a target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event.
In some alternative embodiments, processor 1101 specifically performs:
and inputting the target object information into a probabilistic reasoning model, and determining the target occurrence probability of each preset travel event according to the preset probability information and the target object information through the probabilistic reasoning model.
In some optional embodiments, the preset probability information includes a first probability that each preset item exists independently when any preset travel event occurs, and a preset occurrence probability of each preset travel event; the processor 1101 specifically performs:
For any preset travel event, carrying out continuous multiplication on first probabilities of independent existence of all target objects when the preset travel event occurs, and obtaining second probabilities of combined existence of all the target objects when the preset travel event occurs;
multiplying the second probability with the preset occurrence probability of the preset travel event to obtain a probability product;
and determining the ratio between the probability product and the third probability of the combined existence of all the target objects as the target occurrence probability of the preset travel event.
In some alternative embodiments, the probabilistic inference model comprises a bayesian network.
In some alternative embodiments, processor 1101 specifically performs:
and determining a preset travel event corresponding to the maximum value of the target occurrence probability as a target travel event corresponding to the package to be tested.
In some alternative embodiments, processor 1101 specifically performs:
determining a preset travel event with the target occurrence probability larger than the occurrence probability threshold as a candidate travel event;
if a plurality of candidate travel events exist, determining the candidate travel event with the highest weight as a target travel event corresponding to the package to be tested; if one candidate travel event exists, determining the candidate travel event as a target travel event corresponding to the package to be tested.
In some alternative embodiments, processor 1101 specifically performs:
inputting the acquired image into an object recognition model, carrying out object recognition on the acquired image through the object recognition model, and determining object information of a recognition object and a confidence coefficient corresponding to the recognition object;
if the confidence coefficient corresponding to the identification object is larger than the preset confidence coefficient, determining the object information of the identification object as the target object information; otherwise, determining the object information of the identified object as background information.
In some alternative embodiments, processor 1101 performs:
determining whether information representing forbidden articles exists in target article information corresponding to the package to be tested;
if the information representing the forbidden articles exists in the target article information, determining whether the package to be tested passes security inspection or not according to the information representing the forbidden articles and a target travel event corresponding to the package to be tested;
and if the information of the forbidden articles is not represented in the information of the target articles, determining that the package to be tested passes the security check.
In some alternative embodiments, processor 1101 specifically performs:
if the target travel event represents safe travel and the information representing forbidden articles is in an article set corresponding to the target travel event, judging that the package to be tested passes security inspection; otherwise, judging that the package to be tested does not pass the security check;
Wherein the item set includes item information for the desired item when the target travel event occurs.
In some alternative embodiments, processor 1101 performs:
determining the occurrence times of each target travel event in a target travel event sequence according to the target travel event sequence corresponding to all packages to be tested in the region to be tested in a preset period;
for any target travel event, if the occurrence times of the target travel event exceeds the preset times corresponding to the target travel event, notifying an event message in a preset notification mode; the event message comprises the target travel event and information representing the region to be tested.
Since the electronic device is the electronic device in the method in the embodiment of the present application, and the principle of solving the problem by the electronic device is similar to that of the method, the implementation of the electronic device may refer to the implementation of the method, and the repetition is not repeated.
Based on the same technical concept, the embodiments of the present application also provide a computer-readable storage medium storing a computer program executable by an electronic device, which when run on the electronic device, causes the electronic device to execute the steps of the above travel event determination method, security inspection method, or event management method based on the package acquired image.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (8)
1. A travel event determination method, comprising:
determining target article information corresponding to a package to be tested according to an acquired image containing the package to be tested; wherein the target item information characterizes a target item in the package to be tested;
determining target occurrence probability of each preset travel event when the target object combination exists according to the target object information;
selecting a target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event;
according to the target item information, determining the target occurrence probability of each preset travel event when the target item combination exists, wherein the method comprises the following steps:
inputting the target object information into a probabilistic reasoning model, and determining the target occurrence probability of each preset travel event according to the preset probability information and the target object information through the probabilistic reasoning model;
The preset probability information comprises a first probability that each preset article exists independently when any preset travel event occurs and a preset occurrence probability of each preset travel event; according to the preset probability information and the target object information, determining the target occurrence probability of each preset travel event comprises the following steps:
for any preset travel event, carrying out continuous multiplication on first probabilities of independent existence of all target objects when the preset travel event occurs, and obtaining second probabilities of combined existence of all the target objects when the preset travel event occurs;
multiplying the second probability with the preset occurrence probability of the preset travel event to obtain a probability product;
and determining the ratio between the probability product and the third probability of the combined existence of all the target objects as the target occurrence probability of the preset travel event.
2. The method of claim 1, wherein the probabilistic inference model comprises a bayesian network.
3. The method according to claim 1 or 2, wherein selecting the target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event comprises:
And determining a preset travel event corresponding to the maximum value of the target occurrence probability as a target travel event corresponding to the package to be tested.
4. The method according to claim 1 or 2, wherein selecting the target travel event corresponding to the package to be tested from all preset travel events according to the target occurrence probability of each preset travel event comprises:
determining a preset travel event with the target occurrence probability larger than the occurrence probability threshold as a candidate travel event;
if a plurality of candidate travel events exist, determining the candidate travel event with the highest weight as a target travel event corresponding to the package to be tested; if one candidate travel event exists, determining the candidate travel event as a target travel event corresponding to the package to be tested.
5. The method according to claim 1 or 2, wherein determining target item information corresponding to a package to be tested based on an acquired image containing the package to be tested, comprises:
inputting the acquired image into an object recognition model, carrying out object recognition on the acquired image through the object recognition model, and determining object information of a recognition object and a confidence coefficient corresponding to the recognition object;
If the confidence coefficient corresponding to the identification object is larger than the preset confidence coefficient, determining the object information of the identification object as the target object information; otherwise, determining the object information of the identified object as background information.
6. A security inspection method, comprising:
determining whether information representing forbidden articles exists in target article information corresponding to the package to be tested;
if the information representing the forbidden articles exists in the target article information, judging whether the package to be tested passes security inspection or not according to the information representing the forbidden articles and the target travel event corresponding to the package to be tested; wherein the target travel event is determined based on the method of any one of claims 1 to 5;
and if the information of the forbidden articles is not represented in the information of the target articles, judging that the package to be tested passes the security check.
7. The method of claim 6, wherein determining whether the package under test passes a security check based on the information characterizing the contraband and the target travel event corresponding to the package under test comprises:
if the target travel event represents safe travel and the information representing forbidden articles is in an article set corresponding to the target travel event, judging that the package to be tested passes security inspection; otherwise, judging that the package to be tested does not pass the security check;
Wherein the item set includes item information for the desired item when the target travel event occurs.
8. An event management method, comprising:
determining the occurrence times of each target travel event in a target travel event sequence according to the target travel event sequence corresponding to all packages to be tested in the region to be tested in a preset period; wherein the target travel event corresponding to each package to be tested is determined based on the method of any one of claims 1 to 5;
for any target travel event, if the occurrence times of the target travel event exceeds the preset times corresponding to the target travel event, notifying an event message in a preset notification mode; the event message comprises the target travel event and information representing the region to be tested.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211384507.2A CN115797857B (en) | 2022-11-07 | 2022-11-07 | Travel event determining method, security inspection method and event management method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211384507.2A CN115797857B (en) | 2022-11-07 | 2022-11-07 | Travel event determining method, security inspection method and event management method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115797857A CN115797857A (en) | 2023-03-14 |
CN115797857B true CN115797857B (en) | 2023-08-01 |
Family
ID=85435835
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211384507.2A Active CN115797857B (en) | 2022-11-07 | 2022-11-07 | Travel event determining method, security inspection method and event management method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115797857B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992530A (en) * | 2017-11-14 | 2018-05-04 | 北京三快在线科技有限公司 | Information recommendation method and electronic equipment |
WO2021073370A1 (en) * | 2019-10-16 | 2021-04-22 | 北京海益同展信息科技有限公司 | Article inspection method, apparatus and system and computer readable storage medium |
WO2022105243A1 (en) * | 2020-11-23 | 2022-05-27 | 北京旷视科技有限公司 | Event detection method, apparatus, electronic device, and storage medium |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107273992A (en) * | 2017-06-20 | 2017-10-20 | 三星电子(中国)研发中心 | A kind of method and apparatus for cooking up every trade journey |
CN109214274B (en) * | 2018-07-19 | 2020-12-29 | 国政通科技有限公司 | Airport security management system |
CN109359755A (en) * | 2018-09-29 | 2019-02-19 | 百度在线网络技术(北京)有限公司 | Event monitoring method, apparatus, equipment and storage medium |
CN113194109A (en) * | 2020-01-14 | 2021-07-30 | 百度在线网络技术(北京)有限公司 | Method and device for pushing information |
CN112270671B (en) * | 2020-11-10 | 2023-06-02 | 杭州海康威视数字技术股份有限公司 | Image detection method, device, electronic equipment and storage medium |
CN112818844A (en) * | 2021-01-29 | 2021-05-18 | 成都商汤科技有限公司 | Security check abnormal event detection method and device, electronic equipment and storage medium |
CN114913480A (en) * | 2022-05-31 | 2022-08-16 | 杭州睿影科技有限公司 | Package detection method, device, system, controller and storage medium |
-
2022
- 2022-11-07 CN CN202211384507.2A patent/CN115797857B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992530A (en) * | 2017-11-14 | 2018-05-04 | 北京三快在线科技有限公司 | Information recommendation method and electronic equipment |
WO2021073370A1 (en) * | 2019-10-16 | 2021-04-22 | 北京海益同展信息科技有限公司 | Article inspection method, apparatus and system and computer readable storage medium |
WO2022105243A1 (en) * | 2020-11-23 | 2022-05-27 | 北京旷视科技有限公司 | Event detection method, apparatus, electronic device, and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN115797857A (en) | 2023-03-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10354406B2 (en) | Method of detecting objects within a 3D environment | |
CN111967387B (en) | Form recognition method, form recognition device, form recognition equipment and computer-readable storage medium | |
US8938357B2 (en) | Characteristic point detection system, characteristic point detection method, and program | |
US8359344B2 (en) | Automatic linking of points of interest for indoor location based searching | |
CN108960266A (en) | Image object detection method and device | |
US20030046297A1 (en) | System and method for a partially self-training learning system | |
CN101496035A (en) | Pattern classification method | |
CN105938480A (en) | RFID redundant data cleansing method and system based on DTBF | |
CN112001173B (en) | Party code management method, apparatus, terminal device and storage medium | |
Li et al. | New automatic incident detection algorithm based on traffic data collected for journey time estimation | |
WO2017036341A1 (en) | Random index pattern matching based email relations finder system | |
US8301584B2 (en) | System and method for adaptive pruning | |
CN115797857B (en) | Travel event determining method, security inspection method and event management method | |
CN113902041A (en) | Target detection model training and identity verification method and device | |
US10726349B2 (en) | Calculating posterior probability of classes | |
US9053579B2 (en) | Selective learning for growing a graph lattice | |
Schwalb | Analysis of hazards for autonomous driving | |
CN111695820A (en) | Engineering vehicle electronic coupon management method and device, terminal and storage medium | |
CN114140751B (en) | Examination room monitoring method and system | |
CN110188519A (en) | A kind of detection method, device and the electronic equipment of exception sliding trace | |
CN116362534A (en) | Emergency management method and system for violations and risks of online customer service contents in railway field | |
CN114067401A (en) | Target detection model training and identity verification method and device | |
CN113762029A (en) | Dangerous goods identification method, device, equipment and storage medium | |
CN114004674A (en) | Model training method, commodity pushing method and device and electronic equipment | |
CN113592031B (en) | Image classification system, and method and device for identifying violation tool |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |